[llvm-bugs] [Bug 35962] New: [AMDGPU][MC] Incorrect encoding of VDATA for image atomics

via llvm-bugs llvm-bugs at lists.llvm.org
Tue Jan 16 04:07:54 PST 2018


https://bugs.llvm.org/show_bug.cgi?id=35962

            Bug ID: 35962
           Summary: [AMDGPU][MC] Incorrect encoding of VDATA for image
                    atomics
           Product: libraries
           Version: trunk
          Hardware: PC
                OS: All
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: Backend: AMDGPU
          Assignee: unassignedbugs at nondot.org
          Reporter: dpreobrazhensky at luxoft.com
                CC: llvm-bugs at lists.llvm.org

VDATA specified in the instruction is not encoded; VADDR is encoded instead.
For example (VI):

image_atomic_add v6, v255, s[8:15] dmask:0x1

    0x00,0x01,0x48,0xf0,0xff,0xff,0x02,0x00 // VADDR=VDATA=0xff

image_atomic_add v252, v2, s[8:15] dmask:0x1

    0x00,0x01,0x48,0xf0,0x02,0x02,0x02,0x00 // VADDR=VDATA=0x02

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20180116/3e78db03/attachment.html>


More information about the llvm-bugs mailing list